Professional Documents
Culture Documents
net/publication/220419649
Multibiometric Systems
CITATIONS READS
336 338
2 authors, including:
Arun Ross
Michigan State University
310 PUBLICATIONS 16,815 CITATIONS
SEE PROFILE
Some of the authors of this publication are also working on these related projects:
All content following this page was uploaded by Arun Ross on 23 November 2014.
Multibiometric
Systems BY ANIL K. JAIN AND
ARUN ROSS
T
raditionally, passwords (knowledge-based security)
and ID cards (token-based security) have been used
to restrict access to secure systems. However, secu-
rity can be easily breached in these systems when a
password is divulged to an unauthorized user or a
card is stolen by an impostor. Furthermore, simple
passwords are easy to guess by an impostor and difficult pass-
words may be hard to recall by a legitimate user. The emergence
of biometrics has addressed the problems that plague traditional
verification methods. Biometrics refers to the automatic identifi-
cation (or verification) of an individual (or a claimed identity) by
using certain physiological or behavioral traits associated with
the person (see Figure 1). By using biometrics
Illustration by Sandra Dionisi
WHILE biometric systems have their limitations they have an edge over
traditional security methods in that they cannot be easily stolen or shared.
Besides bolstering security, biometric systems also enhance user convenience
by alleviating the need to design and remember passwords. Moreover, biometrics
is one of the few techniques that can be used for negative recognition where
the system determines whether the person is who he or she denies to be.
modes—the identification mode, in which the iden-
tity of an unknown user is determined, and the veri-
fication mode, in which a claimed identity is either
accepted (a genuine user) or rejected (an impostor).
Biometric systems are being deployed in various
applications including computer logins, ATMs, gro-
cery stores, airport kiosks, and driver’s licenses. The
successful installation of biometric systems in these
apºplications does not imply that biometrics is a
solved problem. In fact, there is significant room for
improvement in biometrics as suggested by the error
rates shown in the table on the next page.
Biometric systems installed in real-world applica-
tions must contend with a variety of problems.
Among them are:
Noise in sensed data. A fingerprint with a scar and a
voice altered by a cold are examples of noisy inputs.
Noisy data could also result from defective or improp-
erly maintained sensors (for example, accumulation of
dirt on a fingerprint sensor) and unfavorable ambient
conditions (for example, poor illumination of a user’s
face in a face recognition system). Noisy biometric
data may be incorrectly matched with templates in the
database resulting in a user being incorrectly rejected.
Intra-class variations. The biometric data acquired failure to enroll (FTE) rate associated with using a sin-
from an individual during authentication may be very gle biometric trait. There is empirical evidence that
different from the data used to generate the template about 4% of the population may have poor quality
during enrollment, thereby affecting the matching fingerprints that cannot be easily imaged by some of
process. This variation the existing sensors.
is typically caused by a Test Test Parameter False Reject False Accept
Spoof attacks. An
user who is incorrectly Rate (FRR) Rate (FAR) impostor may attempt
interacting with the Fingerprint FVC 2002* Users mostly in the age 0.2% 0.2% to spoof the biometric
group 20-39
sensor, or when sensor trait of a legitimately
FRVT 2002** Enrollment and test images
characteristics are modi- Face were collected in indoor
10% 1%
enrolled user in order
fied (for example, by environment and
be on different days
could to circumvent the sys-
changing sensors, that Voice NIST 2000*** Text dependent 10-20% 2-5%
tem. This type of attack
is, the sensor interoper- *Fingerprint Verification Competition; bias.csr.unibo.it/fvc2002 is especially relevant
ability problem) during **Face Recognition Vendor Test; www.frvt.org/FRVT2002
***National Institute of Standards and Technology; www.nist.gov/speech/tests/spk/2000
when behavioral traits
authentication. such as signature and
Distinctiveness. While a biometric trait is expected State-of-the-art error rates voice are used. However,
to vary significantly across individuals, there may be associated with fingerprint, face, physical traits like finger-
and voice biometric systems. The
large similarities in the feature sets used to represent accuracy estimates of biometric prints are also susceptible
these traits. Thus, every biometric trait has some the- systems depend on a number of to spoof attacks.
oretical upper bound in terms of its discrimination test conditions.
capability. Multibiometric Systems
Non-universality. While every user is expected to Some of the limitations imposed by unimodal bio-
possess the biometric trait being acquired, in reality it metric systems (that is, biometric systems that rely
is possible for a subset of the users to not possess a par- on the evidence of a single biometric trait) can be
ticular biometric. A fingerprint biometric system, for overcome by using multiple biometric modalities [1,
example, may be unable to extract features from the 2, 6]. Such systems, known as multibiometric sys-
fingerprints of certain individuals, due to the poor tems, are expected to be more reliable due to the
quality of the ridges (see Figure 2a). Thus, there is a presence of multiple, fairly independent pieces of
live user is indeed present at the point of data acqui- Figure 2a. The failure-to-access to information at this
sition. Thus, a challenge-response type of authenti- enroll (FTE) problem as level. Second, the feature
observed in fingerprints.
cation can be facilitated using multibiometric The four impressions of a spaces of different biometric
systems. user’s fingerprint shown traits may not be compatible.
here cannot be enrolled by
A variety of factors should be considered when most fingerprint
For example, it is difficult to
designing a multibiometric system. These include the systems, due to the combine the minutiae feature
choice and number of biometric traits; the level in the poor image quality of the set of a fingerprint image with
ridges. Consequently,
biometric system at which information provided by alternate methods must be the eigen-coefficients of a face
multiple traits should be integrated; the methodology adopted in order to image. Third, even if the fea-
adopted to integrate the information; and the cost include this user in the ture sets were compatible,
system.
versus matching performance trade-off. concatenation might result in
The choice and number of biometric traits is a feature vector with a very large dimensionality lead-
largely driven by the nature of the application, the ing to the “curse of dimensionality” problem. Fusion
overhead introduced by multiple traits (computa- at the decision level is considered rigid due to the
tional demands and cost, for example), and the corre- availability of limited information. In fact, the only
lation between the traits considered. In a cell phone type of information available at this level is an
equipped with a camera it might be easier to combine “Accept” or a “Reject” label in the verification mode,
the face and voice traits of a user, while in an ATM or the identity of the user in the identification mode.
application it might be easier to combine the finger- Due to the reasons stated here, fusion at the
print and face traits of the user. A commercial multi- matching score level is usually preferred, as it is rel-
biometric system called BioID (www.bioid.com) atively easy to access and combine the scores pre-
integrates the face, voice, and lip movement of an sented by the different modalities. Note that fusion
individual. at this level is a practical compromise between
The information presented by multiple traits may fusion at the other two levels. In the context of ver-
be consolidated at various levels.1 At the feature ification, two distinct approaches exist for fusion at
extraction level, the feature sets of multiple modalities this level. In the first approach the fusion is viewed
are integrated and a new feature set is generated; the as a classification problem where a feature vector is
new feature set is then used in the matching and deci- constructed using the matching scores output by the
individual matchers; this feature vector is then clas-
1
Apart from the three levels mentioned here, fusion is also possible at the sensor level
sified into one of two classes: “Accept” (genuine
and rank level [3]. user) or “Reject” (impostor) [9]. In the second
References
1. Bigun, E.S., Bigun, J., Duc, B., and Fischer, S. Expert conciliation for
multimodal person authentication systems using Bayesian statistics.
In Proceedings of the International Conference on Audio and Video-
Based Biometric Person Authentication. (Crans-Montana, Switzerland,
Mar. 1997), 291–300.
2. Brunelli, R., and Falavigna, D. Person identification using multiple
cues. IEEE Trans. on Pattern Analysis and Machine Intelligence 12, 10
(Oct. 1995). IEEE, NY, 955–966.
3. Ho, T.K. Hull, J.J., and Srihari, S.N. Decision combination in mul-
tiple classifier systems. IEEE Trans. on Pattern Analysis and Machine
Intelligence 16, 1 (1994), IEEE, NY, 66–75.
4. Jain, A.K., Bolle, R., and Pankanti, S. (Eds.). Biometrics: Personal
Identification in Networked Society. Kluwer, Dordrecht, The Nether-
lands, 1999.
5. Jain, A.K., and Ross, A. Learning user-specific parameters in a multi-
biometric system. In Proceedings of the IEEE International Conference
on Image Processing (Rochester, NY, Sept. 22–25, 2002), 57–60.
6. Kittler, J., Hatef, M., Duin, R., and Matas, J. On combining classifiers.
Figure 3. Eliminating false rejects by employing user-specific IEEE Trans. on Pattern Analysis and Machine Intelligence 20, 3 (Mar.
weights. (a), (c), and (e) are templates, and (b), (d), and (f) are 1998). IEEE, NY, 226–239.
the corresponding test samples (from the same user). At a 7. Ross, A., and Jain, A.K. Information fusion in biometrics. Pattern Recog-
matching threshold of 50, equal weighting of the three nition Letters 24, 13 (Sept. 2003), 2115–2125.
normalized matching scores (for fingerprint, hand geometry, 8. Snelick, R., Indovina, M., Yen, J., and Mink, A. Multimodal biometrics:
and face) results in a false reject of this user, while user-specific Issues in design and testing. In Proceedings of International Conference on
weighting (weights of 0.6, 0.2, and 0.2 for fingerprint, hand and Multimodal Interfaces (Vancouver, B.C., Nov. 5–7, 2003).
face, respectively) results in a correct acceptance of the user. 9. Verlinde, P., and Cholet, G. Comparing decision fusion paradigms
using k-NN based classifiers, decision trees and logistic regression in a
multi-modal identity verification application. In Proceedings of the Inter-
imental results indicate that employing user-specific national Conference on Audio and Video-Based Biometric Person Authen-
tication. (Washington, D.C., Mar. 1999), 188–193.
weights further improves matching performance [5].